Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/SecurityTalent/bugskill-ainpx agentmods add skills/securitytalent/bugskill-ai/sandbox-escape-techniquesWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/securitytalent/bugskill-ai/sandbox-escape-techniques)<a href="https://agentmods.dev/skills/securitytalent/bugskill-ai/sandbox-escape-techniques"><img src="https://agentmods.dev/badge/skills/securitytalent/bugskill-ai/sandbox-escape-techniques/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/securitytalent/bugskill-ai/sandbox-escape-techniques"><img src="https://agentmods.dev/badge/skills/securitytalent/bugskill-ai/sandbox-escape-techniques.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00049 | $0.02442 |
| Opus 5.5 | $0.00020 | $0.00977 |
| Sonnet 5.5 | $0.00010 | $0.00488 |
| Haiku 4.5 | $0.00005 | $0.00244 |
Grade E, and why
sandbox-escape-techniques scanned grade E with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reaches for credential fileshighPrivilege escalation
SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.
cat /proc/1/root/etc/shadow # read host files Encoded or obfuscated payloadhighSupply chain
base64 or hex that is decoded and executed hides what actually runs from anyone reading the file.
| Encoding | `echo /bin/bash | base64 -d | sh` | This is a copy
100% identical to sandbox-escape-techniques — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 251 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SKILL: Sandbox Escape — Expert Attack Playbook
AI LOAD INSTRUCTION: Expert sandbox escape techniques across Python, Lua, seccomp, chroot, Docker/container, and browser sandbox contexts. Covers CTF pyjail patterns, seccomp architecture confusion, chroot fd leaks, namespace escape, and Mojo IPC abuse. Distilled from ctf-wiki sandbox sections and real-world container escapes. Base models often miss the distinction between sandbox types and apply wrong escape techniques.
0. RELATED ROUTING
- browser-exploitation-v8 — V8 exploitation for renderer RCE before browser sandbox escape
- container-escape-techniques — Docker/container specific escape techniques
- kernel-exploitation — kernel exploit for container/namespace escape
- linux-privilege-escalation — post-escape privilege escalation
Advanced References
- PYTHON_SANDBOX_ESCAPE.md — Full pyjail methodology:
__builtins__recovery, keyword bypass, AST bypass, pickle escape - SECCOMP_BYPASS.md — Architecture confusion, io_uring bypass, ptrace bypass, allowed syscall chaining
1. SANDBOX TYPE IDENTIFICATION
| Sandbox Type | Indicators | Typical Context |
|---|---|---|
| Python sandbox (pyjail) | Limited builtins, filtered keywords, exec/eval available |
CTF, online judges, Jupyter |
| Lua sandbox | No os, io modules; restricted metatables |
Game scripting, config |
| seccomp | syscall filtering, prctl(PR_SET_SECCOMP) |
CTF pwn, container hardening |
| chroot | Changed root filesystem, limited /proc access |
Legacy isolation |
| Docker/container | Namespaces, cgroups, reduced capabilities | Cloud, microservices |
| Browser (renderer) | OS-level sandbox (seccomp-bpf + namespaces on Linux) | Chrome, Firefox |
| Namespace isolation | PID/mount/network/user namespace | Container runtimes |
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 251 lines · 49 tokens per session scan E ea0ddc8359cf
sandbox-escape-techniques is a skill published in the GitHub repository SecurityTalent/bugskill-ai (13 stars, last pushed 21d ago), licensed MIT. It adds 49 tokens to every session and 2,442 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it E with 2 findings (reaches for credential files, encoded or obfuscated payload). It is 100% identical to sandbox-escape-techniques, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
vmware-vks
Use this skill whenever the user needs to manage vSphere Kubernetes Service (VKS) — Supervisor clusters, vSphere Namespaces, and TKC cluster lifecycle. Directly handles: check VKS compatibility, create/delete namespaces, create/scale/upgrade/delete TKC clusters, get kubeconfig, check Harbor registry. Always use this…
dockerfile-optimizer
Audits Dockerfiles for multi-stage build efficiency, layer caching, non-root security, and minimal base image footprint.
Kubernetes编排
A guide for using Kubernetes, a system that deploys and manages containerized applications across servers.
Kubernetes验证器
A guide for checking Kubernetes configuration files, commonly written in YAML, and the resources they define.
Docker容器化
A guide for packaging applications in Docker containers, including architecture, configuration, performance, and microservice design.
容器镜像管理
A guide for managing container images, which are packaged files used to create running containers, in image repositories.